lucidrains / rela-transformerView external linksLinks
Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012
☆49Apr 6, 2022Updated 3 years ago
Alternatives and similar repositories for rela-transformer
Users that are interested in rela-transformer are comparing it to the libraries listed below
Sorting:
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆36Sep 27, 2021Updated 4 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Oct 9, 2022Updated 3 years ago
- This is project for korean auto spacing☆12Aug 3, 2020Updated 5 years ago
- Visual search interface☆11Nov 30, 2021Updated 4 years ago
- Local Attention - Flax module for Jax☆22May 26, 2021Updated 4 years ago
- ☆11Oct 3, 2021Updated 4 years ago
- Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorc…☆171Nov 25, 2022Updated 3 years ago
- We can crawl NaverBlog, Twitter, Youtube!!☆14Sep 13, 2019Updated 6 years ago
- Pytorch implementation of the hamburger module from the ICLR 2021 paper "Is Attention Better Than Matrix Decomposition"☆99Jan 13, 2021Updated 5 years ago
- Image restoration with neural networks but without learning.☆46May 12, 2022Updated 3 years ago
- Axial Positional Embedding for Pytorch☆84Feb 25, 2025Updated 11 months ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆16Aug 3, 2021Updated 4 years ago
- GAU-alpha-pytorch☆20May 11, 2022Updated 3 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆49Jan 27, 2022Updated 4 years ago
- ☆21Feb 21, 2022Updated 3 years ago
- Implementation of a holodeck, written in Pytorch☆18Nov 1, 2023Updated 2 years ago
- A JAX nn library☆22Sep 9, 2025Updated 5 months ago
- Korean text data preprocess toolkit for NLP☆18Jun 11, 2019Updated 6 years ago
- Standalone Product Key Memory module in Pytorch - for augmenting Transformer models☆87Nov 1, 2025Updated 3 months ago
- Adam with minor modifications which give significant improvement☆19Aug 20, 2021Updated 4 years ago
- ESGD-M is a stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch.☆55Sep 18, 2022Updated 3 years ago
- A smart web crawler built in Rust that uses Claude AI to select the most relevant URLs from website sitemaps based on crawling objectives…☆19Jul 9, 2025Updated 7 months ago
- ☆13Dec 13, 2022Updated 3 years ago
- Implementation of E(n)-Transformer, which incorporates attention mechanisms into Welling's E(n)-Equivariant Graph Neural Network☆226Jun 2, 2024Updated last year
- Graph neural network message passing reframed as a Transformer with local attention☆70Dec 24, 2022Updated 3 years ago
- Korean Named Entity Corpus☆25May 12, 2023Updated 2 years ago
- ☆26Feb 15, 2023Updated 3 years ago
- Unofficial PyTorch Implementation of OpenAI's GPT-3☆13Apr 11, 2022Updated 3 years ago
- Paper Review about Speech Recognition · NLP☆10Mar 25, 2021Updated 4 years ago
- AI model designed to test the effectiveness in handling external ethical attacks.☆11Feb 9, 2026Updated last week
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆47Jul 16, 2023Updated 2 years ago
- Implementation of Insertion-deletion Denoising Diffusion Probabilistic Models☆30May 31, 2022Updated 3 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Jan 10, 2022Updated 4 years ago
- Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch☆46Mar 3, 2021Updated 4 years ago
- The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).☆564Jul 13, 2023Updated 2 years ago
- Code for ICLR 2021 Paper, "Anytime Sampling for Autoregressive Models via Ordered Autoencoding"☆26Jun 6, 2023Updated 2 years ago
- Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)☆102Nov 2, 2020Updated 5 years ago
- Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, de…☆102Apr 22, 2022Updated 3 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Nov 30, 2021Updated 4 years ago